Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,35 @@
|
|
1 |
-
---
|
2 |
-
license: mit
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
language:
|
4 |
+
- en
|
5 |
+
base_model:
|
6 |
+
- mistralai/Mistral-7B-v0.1
|
7 |
+
pipeline_tag: question-answering
|
8 |
+
tags:
|
9 |
+
- technology
|
10 |
+
- QA
|
11 |
+
---
|
12 |
+
# TechChat
|
13 |
+
|
14 |
+
**TechChat** is a domain-specific chatbot fine-tuned from [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) using LoRA.
|
15 |
+
|
16 |
+
## Model Details
|
17 |
+
- **Base model:** mistralai/Mistral-7B-v0.1
|
18 |
+
- **Fine-tuning method:** LoRA (Low-Rank Adaptation)
|
19 |
+
- **Max sequence length:** 512 tokens
|
20 |
+
|
21 |
+
## Intended Use
|
22 |
+
- Technical Q&A in [your domain]
|
23 |
+
- Chat-style interactions
|
24 |
+
|
25 |
+
## Example
|
26 |
+
```python
|
27 |
+
from transformers import AutoTokenizer, AutoModelForCausalLM
|
28 |
+
|
29 |
+
model = AutoModelForCausalLM.from_pretrained("hari7261/TechChat")
|
30 |
+
tokenizer = AutoTokenizer.from_pretrained("hari7261/TechChat")
|
31 |
+
|
32 |
+
prompt = "Explain DNS in simple terms."
|
33 |
+
inputs = tokenizer(prompt, return_tensors="pt")
|
34 |
+
outputs = model.generate(**inputs, max_new_tokens=150)
|
35 |
+
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|